© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8649
    Prev
    Next
    INDEX
    Explanations

    expressions related to electrical engineering concepts, particularly focusing on phase relationships and directional movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Reverse direction or reversed orientation

    np_acts-logits-general · gemini-2.0-flash

    reverse direction or flipped state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ename
    -0.58
    sizeCache
    -0.55
    ktan
    -0.54
     multifunctional
    -0.53
     thinly
    -0.53
    onViewCreated
    -0.52
     ename
    -0.52
    вень
    -0.51
     Milestone
    -0.51
    tache
    -0.50
    POSITIVE LOGITS
     reverse
    1.29
     reversed
    1.22
     Reverse
    1.19
    reverse
    1.17
     reverses
    1.16
    Reverse
    1.12
     reversal
    1.10
     reversing
    1.07
    Reversed
    1.00
    reversed
    0.97
    Activations Density 0.998%

    No Known Activations